Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4563 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3866. Min Act: -0.0000

Data Index: 230602 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3390. Min Act: 0.0000

Data Index: 335613 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1123215 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3232. Min Act: -0.0000

Data Index: 67564 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3102. Min Act: -0.0000

Data Index: 16876 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1037343 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1163159 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3062. Min Act: 0.0001

Data Index: 862888 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2976. Min Act: -0.0000

Data Index: 220232 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1234583 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2970. Min Act: -0.0000

Data Index: 906868 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3079. Min Act: -0.0000

Data Index: 565996 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3436. Min Act: -0.0000

Data Index: 827918 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2979. Min Act: 0.0000

Data Index: 100316 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2930. Min Act: 0.0001

Data Index: 907377 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2847. Min Act: -0.0000

Data Index: 704118 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2927. Min Act: -0.0000

Data Index: 491788 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1173202 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2795. Min Act: -0.0000

Data Index: 783696 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1097688 (C4 (Web Text))

Max Activating Token Index: 441